StackLégal

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds value with the return-shape equivalence ('same object as GET /api/v1/providers/{slug}') and the language default behavior. It stops short of describing error cases when no fiche matches.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: the primary operation and identifier forms lead, then the return-shape note, then the language default. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by naming the equivalent REST endpoint so the agent can infer the return object, and it covers the lang default. Only the no-match/error behavior is left unstated for this simple read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented in the schema. The description only reinforces that lang defaults to French and gives an alias example ('ga'), adding marginal meaning beyond the structured fields. Baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (look up) and resource (one StackLégal provider fiche), and explicitly enumerates the three accepted identifier forms (canonical slug, alias, exact catalog name). This clearly separates it from the sibling list_providers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies single-record retrieval versus listing, and warns that a name match is not a legal qualification, but never explicitly routes to alternatives (e.g. 'use list_providers to enumerate'). Usage context is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral detail beyond that: unknown slugs go to an 'unknown' field and the rest of the call still succeeds, plus the 81-item cap and default French locale.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences, front-loaded with the purpose and the id-handling rules; nothing is padded. The 'Same payload as GET /api/v1/providers' sentence is only marginally useful to an agent that never sees the REST surface.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read tool with full annotation coverage and no output schema, the description covers the important edge cases (partial failure via 'unknown', item cap, ordering, locale default). It stops short of describing pagination or the exact response shape, but that is a minor gap here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description genuinely adds meaning: the 81-slug maximum, order preservation, and how unknown slugs are handled rather than failing the call. The lang default of French largely repeats the schema wording, which caps this below 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List StackLégal provider fiches') and clarifies scope: specific slugs via ids or the full catalog when omitted. It does not explicitly contrast itself with the sibling get_provider (single-provider fetch), so differentiation is only implicit through naming.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear selection rules: pass ids for specific slugs, omit for the full catalog, with a hard limit of 81 and preserved ordering. It never names get_provider as the alternative for a single record, so the when-not condition is inferred rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations' safety profile: no JavaScript execution, results limited to the first HTML response and Set-Cookie headers only, no consent cookie sent, address and caller IP not stored, and an explicit rate limit of a few scans per 10 minutes. It also disclaims legal qualification, which guards against over-interpreting results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences, each carrying distinct load: scope, method limits, output contents, privacy, rate limit. The core operation is front-loaded in the first clause; nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description still tells the agent what comes back (tracker list with provider slugs where the catalog maps to a fiche, plus a link to the scanner page). Privacy, rate limit, and the legal caveat round out what an agent needs to call and interpret this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and there is a single parameter, so the schema already documents the URL format (http/https, ports 80/443, no username). The description restates 'public URL' and the no-consent condition without adding parameter-level syntax or format detail beyond the schema, matching the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (fetch/report) and resource (one public URL's HTML response and Set-Cookie headers) with the precise scope: single fetch, no consent cookie, no JS execution. This is clearly a one-off site scan, readily distinguishable from catalog lookups like get_provider/list_providers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'before consent' framing implies the use case and the rate limit signals it is not for bulk work, but the description never explicitly says when to choose this over the sibling provider-catalog tools or when not to scan. Usage is inferable rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.